##########################文件开始fileDect.py#############################
#encoding:utf8
# Detect file encoding
# Simple method that just chacks that first 1000 lines are valid in each encoding
# and chooses first from set that is valid for all lines checked.
# A better version would allow for a small proportion of failures and rank encodings
# depending on how well they match the input.
import sys
import os
encodings = [
['utf-8', 65001, 0],
['cp932', 932, 128],
['cp936', 936, 134],
['cp949', 949, 129],
['cp950', 950, 136],
]
codings = [e[0] for e in encodings]
def EncodingWorks(encoding, text):
try:
text.decode(encoding)
return True
except UnicodeDecodeError:
return False
# Read up to first 1000 lines of file
if len(sys.argv) > 1 and os.path.isfile(sys.argv[1]):
with open(sys.argv[1], "rb") as f:
lineNumber = 1
for line in f.readlines():
# Filter out any encodings that fail
codings = [c for c in codings if EncodingWorks(c, line)]
lineNumber += 1
if lineNumber > 1000:
break
codingsKnow = False
comment = ''
for c in codings:
for e in encodings:
if e[0] == c:
codingsKnow = True
codePage, characterSet = e[1:]
if codePage:
print('%scode.page=%s' % (comment, codePage))
if characterSet:
print('%scharacter.set=%s' % (comment, characterSet))
# Display other matches as comments so can check results
comment = '#'
#如果检测不出文件的编码，将默认编码设置成cp936（GBK）
if codingsKnow==False:
print 'code.page=936'
print 'character.set=134'
# Change the caret colour so we can see that something happened
print('caret.fore=#4499FF')
############################文件结束#######################################
然后在配置文件SciTEGlobal.properties中加入
command.discover.properties=python /path/to/fileDetect.py "$(FilePath)"
即可自动检测文件编码，上面的文件可以检测utf-8,gbk,big5等编码，足够使用。
ps.上面的代码是别人写的。。。在linux上测试通过，需要安装python环境
由于是直接复制成网页的，直接拷贝到代码文件可能有问题
Encodings
SciTE will automatically detect the encoding scheme used for Unicode files that start with a Byte Order Mark (BOM). The UTF-8 and UTF-16 encodings are recognised including both Little Endian and Big Endian variants of UTF-16.
UTF-8 files will also be recognised when they contain a coding cookie on one of the first two lines. A coding cookie looks similar to "coding: utf-8" ("coding" followed by ':' or '=', optional whitespace, optional quote, "utf-8") and is normally contained in a comment:
# -*- coding: utf-8 -*-
For XML there is a declaration:
<?xml version='1.0' encoding='utf-8'?>
For other encodings set the code.page and character.set properties.
